TensorFlow官方文档入门笔记[一]
张量
|
3 # a rank 0 tensor; this is a scalar with shape [] [1., 2., 3.] # a rank 1 tensor; this is a vector [[1., 2., 3.], [4., 5., 6.]] # a rank 2 tensor; a matrix with shape [2, 3] [[[1., 2., 3.]], [[7., 8., 9.]]] # a rank 3 tensor with shape [2, 1, 3] |
计算图
TF由两个部分组成：构建计算图与运行计算图。
|
node1 = tf.constant(3.0, dtype=tf.float32) node2 = tf.constant(4.0) # also tf.float32 implicitly print(node1, node2) 输出： Tensor("Const:0", shape=(), dtype=float32) Tensor("Const_1:0", shape=(), |
必须创建一个Session对象，然后调用其run方法运行计算图。会话封装了TensorFlow运行时的控制和状态。
|
sess = tf.Session() print(sess.run([node1, node2])) 输出： [3.0, 4.0] |
|
node3 = tf.add(node1, node2) print("node3:", node3) print("sess.run(node3):", 输出： node3: Tensor("Add:0", shape=(), dtype=float32) sess.run(node3): 7.0 |
a = tf.placeholder(tf.float32) b = tf.placeholder(tf.float32) adder_node = a + b # + provides a shortcut for tf.add(a, b) print(sess.run(adder_node, {a: 3, b: 4.5}))
print(sess.run(adder_node, {a: [1, 3], b: [2, 4]}))
输出 7.5[ 3. 7.] |
add_and_triple = adder_node * 3.
print(sess.run(add_and_triple, {a: 3, b: 4.5}))
输出 22.5 |
变量允许我们向图中添加可训练的参数。它们的构造类型和初始值：
W = tf.Variable([.3], dtype=tf.float32) b = tf.Variable([-.3], dtype=tf.float32) x = tf.placeholder(tf.float32) linear_model = W * x + b |
常数在调用时被初始化tf.constant，其值永远不会改变。相比之下，调用时，变量不会被初始化tf.Variable。要初始化TensorFlow程序中的所有变量：
init = tf.global_variables_initializer() sess.run(init) |
x是占位符评估linear_model几个值
print(sess.run(linear_model, {x: [1, 2, 3, 4]}))
输出 [ 0. 0.30000001 0.60000002 0.90000004] |
评估训练模型创建损失函数
y = tf.placeholder(tf.float32)
squared_deltas = tf.square(linear_model - y)
loss = tf.reduce_sum(squared_deltas)
print(sess.run(loss, {x: [1, 2, 3, 4], y: [0, -1, -2, -3]}))
输出 23.66 |
tf.assign参数值
fixW = tf.assign(W, [-1.])
fixb = tf.assign(b, [1.])
sess.run([fixW, fixb])
print(sess.run(loss, {x: [1, 2, 3, 4], y: [0, -1, -2, -3]}))
输出 0.0 |
tf.train API
TensorFlow提供了优化器，可以缓慢地更改每个变量，以便最大限度地减少损失函数。最简单的优化器是梯度下降。它根据相对于该变量的损失导数的大小修改每个变量tf.gradients
例如：
optimizer = tf.train.GradientDescentOptimizer(0.01) train = optimizer.minimize(loss) sess.run(init) # reset values to incorrect defaults.
for i in range(1000):
sess.run(train, {x: [1, 2, 3, 4], y: [0, -1, -2, -3]})
print(sess.run([W, b]))
输出 [array([-0.9999969], dtype=float32), array([ 0.99999082], dtype=float32)] |
完成程序
完成的可训练线性回归模型如下：
import tensorflow as tf
# Model parameters
W = tf.Variable([.3], dtype=tf.float32)
b = tf.Variable([-.3], dtype=tf.float32)
# Model input and output
x = tf.placeholder(tf.float32)
linear_model = W * x + b
y = tf.placeholder(tf.float32)
# loss
loss = tf.reduce_sum(tf.square(linear_model - y)) # sum of the squares
# optimizer
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)
# training data
x_train = [1, 2, 3, 4]
y_train = [0, -1, -2, -3]
# training loop
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init) # reset values to wrong
for i in range(1000):
sess.run(train, {x: x_train, y: y_train})
# evaluate training accuracy
curr_W, curr_b, curr_loss = sess.run([W, b, loss], {x: x_train, y: y_train})
print("W: %s b: %s loss: %s"%(curr_W, curr_b, curr_loss))
输出 W: [-0.9999969] b: [ 0.99999082] loss: 5.69997e-11 |